scikit-learn · rth · Aug 26, 2018 · Jul 6, 2018 · Jul 27, 2018 · Jul 27, 2018
diff --git a/doc/modules/ensemble.rst b/doc/modules/ensemble.rst
@@ -975,7 +975,8 @@ The following example shows how to fit the majority rule classifier::
    >>> iris = datasets.load_iris()
    >>> X, y = iris.data[:, 1:3], iris.target
 
-   >>> clf1 = LogisticRegression(random_state=1)
+   >>> clf1 = LogisticRegression(solver='lbfgs', multi_class='multinomial',
+   ...                           random_state=1)
    >>> clf2 = RandomForestClassifier(n_estimators=50, random_state=1)
    >>> clf3 = GaussianNB()
 
@@ -984,10 +985,10 @@ The following example shows how to fit the majority rule classifier::
    >>> for clf, label in zip([clf1, clf2, clf3, eclf], ['Logistic Regression', 'Random Forest', 'naive Bayes', 'Ensemble']):
    ...     scores = cross_val_score(clf, X, y, cv=5, scoring='accuracy')
    ...     print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))
-   Accuracy: 0.90 (+/- 0.05) [Logistic Regression]
+   Accuracy: 0.95 (+/- 0.04) [Logistic Regression]
    Accuracy: 0.94 (+/- 0.04) [Random Forest]
    Accuracy: 0.91 (+/- 0.04) [naive Bayes]
-   Accuracy: 0.95 (+/- 0.05) [Ensemble]
+   Accuracy: 0.95 (+/- 0.04) [Ensemble]
 
 
 Weighted Average Probabilities (Soft Voting)
@@ -1060,7 +1061,8 @@ The `VotingClassifier` can also be used together with `GridSearch` in order
 to tune the hyperparameters of the individual estimators::
 
    >>> from sklearn.model_selection import GridSearchCV
-   >>> clf1 = LogisticRegression(random_state=1)
+   >>> clf1 = LogisticRegression(solver='lbfgs', multi_class='multinomial',
+   ...                           random_state=1)
    >>> clf2 = RandomForestClassifier(random_state=1)
    >>> clf3 = GaussianNB()
    >>> eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2), ('gnb', clf3)], voting='soft')

diff --git a/doc/modules/linear_model.rst b/doc/modules/linear_model.rst
@@ -775,15 +775,20 @@ The "saga" solver [7]_ is a variant of "sag" that also supports the
 non-smooth `penalty="l1"` option. This is therefore the solver of choice
 for sparse multinomial logistic regression.
 
-In a nutshell, one may choose the solver with the following rules:
-
-=================================  =====================================
-Case                               Solver
-=================================  =====================================
-L1 penalty                         "liblinear" or "saga"
-Multinomial loss                   "lbfgs", "sag", "saga" or "newton-cg"
-Very Large dataset (`n_samples`)   "sag" or "saga"
-=================================  =====================================
+In a nutshell, the following table summarizes the solvers characteristics:
+
+============================   ===========  =======  ===========  =====  ======
+solver                         'liblinear'  'lbfgs'  'newton-cg'  'sag'  'saga'
+============================   ===========  =======  ===========  =====  ======
+Multinomial + L2 penalty       no           yes      yes          yes    yes
+OVR + L2 penalty               yes          yes      yes          yes    yes
+Multinomial + L1 penalty       no           no       no           no     yes
+OVR + L1 penalty               yes          no       no           no     yes
+============================   ===========  =======  ===========  =====  ======
+Penalize the intercept (bad)   yes          no       no           no     no
+Faster for large datasets      no           no       no           yes    yes
+Robust to unscaled datasets    yes          yes      yes          no     no
+============================   ===========  =======  ===========  =====  ======
 
 The "saga" solver is often the best choice. The "liblinear" solver is
 used by default for historical reasons.

diff --git a/doc/tutorial/statistical_inference/supervised_learning.rst b/doc/tutorial/statistical_inference/supervised_learning.rst
@@ -374,12 +374,13 @@ function or **logistic** function:
 
 ::
 
-    >>> logistic = linear_model.LogisticRegression(C=1e5)
-    >>> logistic.fit(iris_X_train, iris_y_train)
+    >>> log = linear_model.LogisticRegression(solver='lbfgs', C=1e5,
+    ...                                       multi_class='multinomial')
+    >>> log.fit(iris_X_train, iris_y_train)  # doctest: +NORMALIZE_WHITESPACE
     LogisticRegression(C=100000.0, class_weight=None, dual=False,
-              fit_intercept=True, intercept_scaling=1, max_iter=100,
-              multi_class='ovr', n_jobs=None, penalty='l2', random_state=None,
-              solver='liblinear', tol=0.0001, verbose=0, warm_start=False)
+        fit_intercept=True, intercept_scaling=1, max_iter=100,
+        multi_class='multinomial', n_jobs=None, penalty='l2', random_state=None,
+        solver='lbfgs', tol=0.0001, verbose=0, warm_start=False)
 
 This is known as :class:`LogisticRegression`.
 

diff --git a/doc/whats_new/v0.20.rst b/doc/whats_new/v0.20.rst
@@ -161,6 +161,7 @@ Support for Python 3.3 has been officially dropped.
   by `Andreas Müller`_ and :user:`Guillaume Lemaitre <glemaitre>`.
 
 
+
 :mod:`sklearn.covariance`
 .........................
 
@@ -504,6 +505,12 @@ Support for Python 3.3 has been officially dropped.
   ValueError.
   :issue:`11327` by :user:`Karan Dhingra <kdhingra307>` and `Joel Nothman`_.
 
+- |API| The default values of the ``solver`` and ``multi_class`` parameters of
+  :class:`linear_model.LogisticRegression` will change respectively from
+  ``'liblinear'`` and ``'ovr'`` in version 0.20 to ``'lbfgs'`` and
+  ``'auto'`` in version 0.22. A FutureWarning is raised when the default
+  values are used. :issue:`11905` by `Tom Dupre la Tour`_ and `Joel Nothman`_.
+
 - |API| Deprecate ``positive=True`` option in :class:`linear_model.Lars` as
   the underlying implementation is broken. Use :class:`linear_model.Lasso`
   instead. :issue:`9837` by `Alexandre Gramfort`_.

diff --git a/sklearn/ensemble/tests/test_bagging.py b/sklearn/ensemble/tests/test_bagging.py
@@ -293,6 +293,8 @@ def test_bootstrap_features():
         assert_greater(boston.data.shape[1], np.unique(features).shape[0])
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 def test_probability():
     # Predict probabilities.
     rng = check_random_state(0)
@@ -712,6 +714,8 @@ def test_oob_score_consistency():
     assert_equal(bagging.fit(X, y).oob_score_, bagging.fit(X, y).oob_score_)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 def test_estimators_samples():
     # Check that format of estimators_samples_ is correct and that results
     # generated at fit time can be identically reproduced at a later time
@@ -748,6 +752,8 @@ def test_estimators_samples():
     assert_array_almost_equal(orig_coefs, new_coefs)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 def test_estimators_samples_deterministic():
     # This test is a regression test to check that with a random step
     # (e.g. SparseRandomProjection) and a given random state, the results

diff --git a/sklearn/ensemble/tests/test_voting_classifier.py b/sklearn/ensemble/tests/test_voting_classifier.py
@@ -28,6 +28,8 @@
 X, y = iris.data[:, 1:3], iris.target
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 def test_estimator_init():
     eclf = VotingClassifier(estimators=[])
     msg = ('Invalid `estimators` attribute, `estimators` should be'
@@ -59,6 +61,8 @@ def test_estimator_init():
     assert_raise_message(ValueError, msg, eclf.fit, X, y)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 def test_predictproba_hardvoting():
     eclf = VotingClassifier(estimators=[('lr1', LogisticRegression()),
                                         ('lr2', LogisticRegression())],
@@ -67,6 +71,8 @@ def test_predictproba_hardvoting():
     assert_raise_message(AttributeError, msg, eclf.predict_proba, X)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 def test_notfitted():
     eclf = VotingClassifier(estimators=[('lr1', LogisticRegression()),
                                         ('lr2', LogisticRegression())],
@@ -76,6 +82,8 @@ def test_notfitted():
     assert_raise_message(NotFittedError, msg, eclf.predict_proba, X)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_majority_label_iris():
     """Check classification by majority label on dataset iris."""
@@ -92,7 +100,8 @@ def test_majority_label_iris():
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_tie_situation():
     """Check voting classifier selects smaller class label in tie situation."""
-    clf1 = LogisticRegression(random_state=123)
+    clf1 = LogisticRegression(random_state=123, multi_class='ovr',
+                              solver='liblinear')
     clf2 = RandomForestClassifier(random_state=123)
     eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2)],
                             voting='hard')
@@ -101,6 +110,8 @@ def test_tie_situation():
     assert_equal(eclf.fit(X, y).predict(X)[73], 1)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_weights_iris():
     """Check classification by average probabilities on dataset iris."""
@@ -115,6 +126,8 @@ def test_weights_iris():
     assert_almost_equal(scores.mean(), 0.93, decimal=2)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_predict_on_toy_problem():
     """Manually check predicted class labels for toy dataset."""
@@ -148,6 +161,8 @@ def test_predict_on_toy_problem():
     assert_equal(all(eclf.fit(X, y).predict(X)), all([1, 1, 1, 2, 2, 2]))
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_predict_proba_on_toy_problem():
     """Calculate predicted probabilities on toy dataset."""
@@ -216,6 +231,8 @@ def test_multilabel():
         return
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_gridsearch():
     """Check GridSearch support."""
@@ -234,6 +251,8 @@ def test_gridsearch():
     grid.fit(iris.data, iris.target)
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_parallel_fit():
     """Check parallel backend of VotingClassifier on toy dataset."""
@@ -256,6 +275,8 @@ def test_parallel_fit():
     assert_array_almost_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_sample_weight():
     """Tests sample_weight parameter of VotingClassifier"""
@@ -300,6 +321,8 @@ def fit(self, X, y, *args, **sample_weight):
     eclf.fit(X, y, sample_weight=np.ones((len(y),)))
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_set_params():
     """set_params should be able to set estimators"""
@@ -335,6 +358,8 @@ def test_set_params():
                  eclf1.get_params()["lr"].get_params()['C'])
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_set_estimator_none():
     """VotingClassifier set_params should be able to set estimators as None"""
@@ -390,6 +415,8 @@ def test_set_estimator_none():
     assert_array_equal(eclf2.transform(X1), np.array([[0], [1]]))
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_estimator_weights_format():
     # Test estimator weights inputs as list and array
@@ -408,6 +435,8 @@ def test_estimator_weights_format():
     assert_array_almost_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @pytest.mark.filterwarnings('ignore:The default value of n_estimators')
 def test_transform():
     """Check transform method of VotingClassifier on toy dataset."""

diff --git a/sklearn/ensemble/voting_classifier.py b/sklearn/ensemble/voting_classifier.py
@@ -90,7 +90,8 @@ class VotingClassifier(_BaseComposition, ClassifierMixin, TransformerMixin):
     >>> from sklearn.linear_model import LogisticRegression
     >>> from sklearn.naive_bayes import GaussianNB
     >>> from sklearn.ensemble import RandomForestClassifier, VotingClassifier
-    >>> clf1 = LogisticRegression(random_state=1)
+    >>> clf1 = LogisticRegression(solver='lbfgs', multi_class='multinomial',
+    ...                           random_state=1)
     >>> clf2 = RandomForestClassifier(n_estimators=50, random_state=1)
     >>> clf3 = GaussianNB()
     >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])

diff --git a/sklearn/feature_selection/tests/test_from_model.py b/sklearn/feature_selection/tests/test_from_model.py
@@ -8,7 +8,6 @@
 from sklearn.utils.testing import assert_greater
 from sklearn.utils.testing import assert_array_almost_equal
 from sklearn.utils.testing import assert_array_equal
-from sklearn.utils.testing import assert_almost_equal
 from sklearn.utils.testing import assert_allclose
 from sklearn.utils.testing import assert_raises
 from sklearn.utils.testing import skip_if_32bit
@@ -178,6 +177,8 @@ def test_feature_importances():
         assert_array_almost_equal(X_new, X[:, feature_mask])
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 def test_sample_weight():
     # Ensure sample weights are passed to underlying estimator
     X, y = datasets.make_classification(
@@ -214,6 +215,8 @@ def test_coef_default_threshold():
     assert_array_almost_equal(X_new, X[:, mask])
 
 
+@pytest.mark.filterwarnings('ignore: Default solver will be changed')  # 0.22
+@pytest.mark.filterwarnings('ignore: Default multi_class will')  # 0.22
 @skip_if_32bit
 def test_2d_coef():
     X, y = datasets.make_classification(